Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add Command Line Option for Model Selection #139

Closed
AntreasAntoniou opened this issue Oct 11, 2023 · 1 comment · Fixed by #219
Closed

Add Command Line Option for Model Selection #139

AntreasAntoniou opened this issue Oct 11, 2023 · 1 comment · Fixed by #219

Comments

@AntreasAntoniou
Copy link

Problem Statement:

The current implementation of Mentat does not allow users to choose which language model to use, including the more advanced GPT-4 and its 32K version.

Proposed Solution:

  • Implement a command-line option, for example, --model, that lets users specify the language model they want to use.
  • Include validation to ensure the specified model is supported.

Acceptance Criteria:

  • A user can specify the model via the command line.
  • The system validates the model name against the supported models and returns an error if it's not supported.

Priority: High

🛠️ This feature is key to user customization and leveraging the full potential of the latest language models.

@biobootloader
Copy link
Member

You can choose the model, as documented here: https://github.com/AbanteAI/mentat/blob/main/docs/configuration.md

But it would be good to have a command line option as well!

@jakethekoenig jakethekoenig linked a pull request Oct 25, 2023 that will close this issue
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.

3 participants